Realizing Text-Driven Motion Generation on NAO Robot: A Reinforcement Learning-Optimized Control Pipeline

TL;DR

This paper presents a novel text-driven motion generation method for the NAO humanoid robot, combining an angle signal network with reinforcement learning to produce stable, human-like movements from textual descriptions.

Contribution

It introduces a new approach that maps text to robot motion using an angle signal network and reinforcement learning, addressing kinematic constraints and stability issues.

Findings

Successfully transfers text descriptions to NAO robot motions

Demonstrates stable and human-like motion execution

Validates effectiveness through real robot experiments

Abstract

Human motion retargeting for humanoid robots, transferring human motion data to robots for imitation, presents significant challenges but offers considerable potential for real-world applications. Traditionally, this process relies on human demonstrations captured through pose estimation or motion capture systems. In this paper, we explore a text-driven approach to mapping human motion to humanoids. To address the inherent discrepancies between the generated motion representations and the kinematic constraints of humanoid robots, we propose an angle signal network based on norm-position and rotation loss (NPR Loss). It generates joint angles, which serve as inputs to a reinforcement learning-based whole-body joint motion control policy. The policy ensures tracking of the generated motions while maintaining the robot's stability during execution. Our experimental results demonstrate the efficacy of this approach, successfully transferring text-driven human motion to a real humanoid robot NAO.